Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, openWorldHint=true and idempotentHint=true, so the bar is low, yet the description adds substantial unstated context: the link expires in ten minutes and works only for that person; the tool itself holds no Google access and connects nothing; Tommo will read their mail and send letters as them; «Tommo work» stays off and past mail is unread until switched on in Settings, Leads. That is exactly the side-effect disclosure an agent needs before triggering a connect flow.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The return value is front-loaded, which is good, but the rest is a single run-on with colon- and guillemet-laden clauses whose nesting makes the important constraints (ten-minute expiry, per-person scope, no Google access held by the tool) hard to extract. The content is nearly all substantive, so this is a packaging problem rather than padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, no parameters and a read-only profile: the description carries the full burden and does — it explains what the link is, its lifetime, who it is valid for, what happens after the person signs in, what stays inactive by default, and how the admin/calendar and Workspace cases differ. Nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes no parameters, so the baseline is 4 and schema coverage is moot. The description correctly implies the identity is taken from the signed-in session rather than from arguments, which is the only parameter-adjacent fact available.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific deliverable — a browser link the signed-in person opens to connect their own mailbox via a single Google sign-in — and immediately contrasts it with the sibling paths (calendar connection piggybacks for admins, Workspace domain-wide delegation goes through add_a_mailbox). An agent can separate this from link_to_connect_a_calendar, link_to_connect_a_tommos_google_account and add_a_mailbox without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the alternative and the condition that selects it: a Google Workspace mailbox whose admin granted domain-wide delegation is added by address via add_a_mailbox instead. It also notes the admin/owner case additionally connects the calendar. It does not spell out a general when-not-to-use boundary, but the sibling routing is clear enough for correct selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.